© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7192
    Prev
    Next
    INDEX
    Explanations

    mentions of collaborative actions involving the speaker and others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and its variations, indicating personal experiences and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tains
    -0.65
     Comes
    -0.61
    lighting
    -0.58
     payday
    -0.57
     citation
    -0.56
     Citation
    -0.54
     URI
    -0.54
     impunity
    -0.54
     api
    -0.52
     Requires
    -0.52
    POSITIVE LOGITS
     alike
    1.04
     ourselves
    1.01
     appreciate
    0.88
     agree
    0.87
     joked
    0.85
     decided
    0.85
     discussed
    0.83
     talked
    0.82
     were
    0.81
     laugh
    0.80
    Activations Density 0.058%

    No Known Activations